Context Windows

Feeds to Scour
SubscribedAll
Scoured 122 posts in 5.6 ms

Efficient and Training-Free Single-Image Diffusion Models

 🎯Fine-tuning

End-to-End Context Compression at Scale

 🤖Transformers  Content type: Academic
arxiv.org·

High Bandwidth Flash | A New Memory for AI Data Centers and Edge Computing | Sandisk

 🤖LLM
ncnonline.net·

Issue #390 - The ML Engineer 🤖

 🤖AI  Content type: News  Content type: Blog

OpenCV 5 release - New DNN engine with enhanced ONNX and LLM/VLM support, Intel, Arm, and RISC-V hardware optimizations - CNX Software

 👁️Computer Vision  Content type: News
cnx-software.com·

BeeLlama.cpp DFlash on Strix Halo: 2.7x Gemma 31B, But MTP Is Still Faster

 Inference Optimization
sleepingrobots.com·

RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference

 🤖LLM  Content type: Academic
arxiv.org·

How LLMs Actually Work: A Friendly Map for Humans • oreoro

 🤖LLM

Benchmarking dots.tts on Strix Halo

 🤖AI
sleepingrobots.com·

Gated DeltaNet, From First Principles

 ✍️Prompt Engineering  Content type: Blog

How to cut the cost of long AI agent threads (without making the agent dumber)

 🤖Agent  Content type: Blog
viktor.com··Hacker News

#065 - Claude writes 80% of Anthropic's own code, Cloudflare buys Vite, ChatGPT ships Dreaming memory

 🔓Open Source
indiehacker.news·

Reality: The Final Eval — Lukas Petersson and Axel Backlund of Andon Labs

 🤖Agent
latent.space··Hacker News

Anatomy of a high-performance EP kernel

 🤖LLM  Content type: Blog

JeevanJoshi2061/titan_engine_core: Constant-memory sequence modeling engine combining selective holographic-compression (ASH-C) with a coordinate pointer network (HEP-DNA). Bypasses the linear KV Cache bottleneck on consumer GPUs.

 🤖LLM  Content type: Code
github.com··Hacker News

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

 🤖LLM  Content type: Academic
arxiv.org··Hacker News

How the UK Is Turning Sovereign AI Ambition Into Action With NVIDIA Technologies

 🎮Reinforcement Learning  Content type: Blog
blogs.nvidia.com·

DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200

 🤖AI  Content type: News

The iPhone’s Last Stand

 🤖Agent

Still: Amortized KV Cache Compaction in a Single Forward Pass

 Inference Optimization  Content type: Academic
arxiv.org·
Sign up or log in to see more results

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help